A three-level multi-fidelity framework (FFT + 3D-CNN + Gaussian-process Bayesian optimization) tunes genetic-algorithm hyperparameters for lattice design, achieving comparable elastic modulus in one-third the generations at 24% lower cost.
Journal of Mechanical Design142(9), 091705 (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bayesian Optimization of Genetic Algorithm Hyperparameters in a Multi-Fidelity Framework for Efficient Lattice Material Design
A three-level multi-fidelity framework (FFT + 3D-CNN + Gaussian-process Bayesian optimization) tunes genetic-algorithm hyperparameters for lattice design, achieving comparable elastic modulus in one-third the generations at 24% lower cost.